Tian Lili, Wu Jianrong
Department of Biostatistics, University at Buffalo, Buffalo, NY 14214, USA.
Stat Med. 2007 Dec 10;26(28):5180-8. doi: 10.1002/sim.2911.
This paper proposes a novel approach for the confidence interval estimation and hypothesis testing of the mean response in a log-regression model using the concept of generalized variable. Simulation studies demonstrate that the proposed confidence intervals have satisfying coverage probabilities. The proposed approach can be simply carried out by a few simulation steps. Therefore, it is an ideal candidate for making inferences about the mean response in a log-regression model.
本文提出了一种使用广义变量概念对对数回归模型中的平均响应进行置信区间估计和假设检验的新方法。模拟研究表明，所提出的置信区间具有令人满意的覆盖概率。所提出的方法可以通过几个模拟步骤简单地实现。因此，它是对对数回归模型中的平均响应进行推断的理想选择。
